Skip to main content
Download PDF

Investigating the effects of artificial intelligence on the personalization of breast cancer management: a systematic study

BMC Cancer volume 24, Article number: 852 (2024) Cite this article

Abstract

Background

Providing appropriate specialized treatment to the right patient at the right time is considered necessary in cancer management. Targeted therapy tailored to the genetic changes of each breast cancer patient is a desirable feature of precision oncology, which can not only reduce disease progression but also potentially increase patient survival. The use of artificial intelligence alongside precision oncology can help physicians by identifying and selecting more effective treatment factors for patients.

Method

A systematic review was conducted using the PubMed, Embase, Scopus, and Web of Science databases in September 2023. We performed the search strategy with keywords, namely: Breast Cancer, Artificial intelligence, and precision Oncology along with their synonyms in the article titles. Descriptive, qualitative, review, and non-English studies were excluded. The quality assessment of the articles and evaluation of bias were determined based on the SJR journal and JBI indices, as well as the PRISMA2020 guideline.

Results

Forty-six studies were selected that focused on personalized breast cancer management using artificial intelligence models. Seventeen studies using various deep learning methods achieved a satisfactory outcome in predicting treatment response and prognosis, contributing to personalized breast cancer management. Two studies utilizing neural networks and clustering provided acceptable indicators for predicting patient survival and categorizing breast tumors. One study employed transfer learning to predict treatment response. Twenty-six studies utilizing machine-learning methods demonstrated that these techniques can improve breast cancer classification, screening, diagnosis, and prognosis. The most frequent modeling techniques used were NB, SVM, RF, XGBoost, and Reinforcement Learning. The average area under the curve (AUC) for the models was 0.91. Moreover, the average values for accuracy, sensitivity, specificity, and precision were reported to be in the range of 90-96% for the models.

Conclusion

Artificial intelligence has proven to be effective in assisting physicians and researchers in managing breast cancer treatment by uncovering hidden patterns in complex omics and genetic data. Intelligent processing of omics data through protein and gene pattern classification and the utilization of deep neural patterns has the potential to significantly transform the field of complex disease management.

Peer Review reports

Introduction

Humans have different genomes, live in different environments, and their physical responses to disease-causing factors and treatments vary. Consequently, standardized therapeutic approaches yield different outcomes in different individuals. Personalized Medicine involves a collection of activities and approaches for appropriate disease management, considering individual-specific characteristics. It provides personalized treatments based on the genomic characteristics of individuals [1] Therefore, the foundation of personalized medicine lies in the identification and classification of individuals and therapeutic methods based on their genetic traits. Thus, personalized medicine can be defined as medicine based on genomic characteristics [2]. Breast cancer is a complex genetic disease caused by genetic mutations [3]. Mutation patterns can vary from one tumor region to another and change over time. This process leads to the creation of genetically distinct subpopulations of cancer cells, which can result in drug resistance in patients [4]. Therefore, identifying molecular differences between tumors is a crucial aspect of precise oncology for selecting the most effective treatment [5]. Precision oncology aims to personalize the therapeutic regimen for each patient based on accurate evaluation of cancer progression or the risk of recurrence, with the goal of achieving effective treatment. Accurately predicting which patients will respond to treatment before they undergo it is a key objective. For example, in breast cancer, the status of the hormone receptor ER is a good indicator of treatment response, but resistance, both intrinsic and acquired after therapy, is common. Therefore, selecting an effective life-saving treatment for the patient is crucial [6]. The study of human genes and proteins (multi-omics) and artificial intelligence are two potential technologies that can transform cancer treatment through precise oncology-guided personalized treatment selection to achieve effectiveness. For example, chemotherapy is the main treatment used for metastatic breast cancer, but the sensitivity and response of different patients to it vary [5,6,7]. For some individuals, it has a significant impact, while for others, its effect may be minimal or non-existent [8, 9]. The ability to predict who will respond to treatment allows for the use of treatment for those who will benefit the most from it. Patients who are not likely to respond can receive alternative treatments and avoid poisoning and side effects of unnecessary drugs [10, 11]. The emerging technologies that investigate the genome and cancer molecules enable scientists to study approximately 500 genes for selecting appropriate treatment in a cancer patient. However, their challenge lies in examining 500 genes in multiple patients, where all their genes change over time, making it complex [12]. This is where artificial intelligence can be effective in discovering patterns of genetic data behavior changes in patients and predicting drug resistance and the protein and cellular mechanisms leading to this resistance. It can help prevent unnecessary drug toxicities and assist oncologists in using expensive drugs when necessary, which result in effective cancer treatment [13]. Moreover, it can prevent unnecessary invasive biopsy, which is a method of guiding cancer cells’ DNA invasion into the bloodstream, which has adverse effects [14, 15]. The main objective of this study is to review the applications of AI algorithms and their effectiveness in personalized medicine approaches. The main objective of this study is to reflect on various machine-learning methods in breast cancer detection and the effectiveness of artificial intelligence applications in precise oncology with the aim of personalized disease management. This investigation can assist scientists and physicians in selecting techniques that have proven to be highly accurate in personalized breast cancer management. They can also have a comprehensive perspective on the personal medical applications in the diagnosis, treatment, and screening of breast cancer.

Materials and methods

The present study is a systematic review based on the PRISMA checklist 2020 [16]. We know that in evidence-based medical research, formulating research questions is considered the most important part of these studies.

Eligibility criteria

Therefore, in this study, the SPICE tool [17], which is a step-by-step framework for formulating questions to find evidence in research, was used. SPICE expands on the PICO acronym (Population, Intervention, Comparison, and Outcomes) in two distinct manners. Firstly, the population component is divided into setting and perspective components. Secondly, the term “outcomes” is substituted with “evaluation” to foster a more comprehensive evaluation framework and merge concepts such as “outputs” and “impact” into one holistic perspective. Efforts were made to select studies from around the world that had used artificial intelligence in personalizing breast cancer management (Setting & Intervention). In these studies, breast cancer patients had benefited from personalized treatment (precision oncology). Ultimately, artificial intelligence had provided a favorable impact on personalizing breast cancer patient management (Evaluation). Considering specific scopes for further exploration, the following questions were designed:

  1. Q1.

    What are the applications of artificial intelligence in precision oncology of breast neoplasms?

  2. Q2.

    Which intelligent artificial intelligence techniques have been used in precision oncology of Breast cancer?

  3. Q3.

    What are the reported effects of artificial intelligence methods, using which indicators, on? Personalizing breast cancer management?

Including and excluding criteria

In order to have a more accurate response to the research questions, certain criteria were considered for selecting articles to be studied. These criteria included: (I) only the article were used, (II) focusing on the investigation, prediction, treatment, screening, and early detection of breast cancer, (III) studies that were based on omics datasets.

Additionally, certain criteria were considered for excluding articles from the study, such as: (I) articles that were not relevant to personalized management of breast cancer, (II) studies that were not in the form of articles (books, conference abstracts), (III) studies where the modeling methodology was not fully explained.

Information sources and search strategy

After determining the research questions, a systematic search was conducted in databases such as PubMed, Web of Science, Scopus, and Embase, for relevant articles published between the years 2015 and 2023, using keywords present in the title, abstract, mesh terms, and key terms. The final search was conducted on January 31st, 2023. The search strategy, and the mesh and emtree terms are presented in the Table 1. The search was performed by combining these two groups of words and using the boolean AND operator. Shortening techniques, phrase search and other related techniques were used in order to conduct a comprehensive search.

Table 1 Vocabulary search formula in databases
Full size table

Screening phase

In the screening phase, both authors (S.S and S.J.E) reviewed the articles based on their titles, abstracts, and eliminated irrelevant articles. In the next phase, the full text of the selected articles was evaluated separately by the two authors using entry/exit criteria. In cases where there was disagreement between the two authors, the issue was resolved through intellectual brainstorming and consensus with the help of a third author (H.M). In the data extraction stage, artificial intelligence models were used to analyze the precise oncology data of breast cancer and performance indices of the models were extracted. The screening methods were performed based on the PRISMA 2020 approach. The quantitative analysis of the data was conducted in the statistical software R. The first author’s name, year, and place of publication of the article were also extracted. Finally, the obtained results were presented in Table 2.

Study risk of bias assessment

To address bias, the Critical Appraisal Checklist from the Joanna Briggs Institute (JBI) [18] was used to evaluate the risk of bias in cross-sectional analytical studies. The checklist was completed by two authors, and in case of disagreement between the two authors, the disagreement was resolved through discussion with the third author. The aim of this evaluation is to appraise the methodological excellence of investigations and comprises seven inquiries in the following order: (1) Were the standards for inclusion in the sample explicitly defined? (2) Were the subjects of the study and the setting comprehensively portrayed? (3) Was the exposure gauged in a legitimate and dependable manner? (4) Were objective, established standards utilized for the measurement of the condition? (5) Were confounding factors recognized? (6) Were approaches to handle confounding factors specified? (7) Were the outcomes gauged in in a valid and reliable way. These inquiries can be addressed employing four alternatives: (1) yes; (2) no; (3) unclear; and (4) not applicable. Each yes response corresponds to one score, and if 70% of the inquiries are responded to “yes” in a study, the risk of partiality was judged to be “low.” If 40 -69% of the inquiries were answered “yes”, the risk of partiality was deemed “moderate,” and below 40% was considered “high risk.”

Processes used to decide which studies were eligible for each synthesis

In this systematic review, the results of studies in which the performance of artificial intelligence techniques were reported quantitatively with indicators of precision, accuracy, specificity, sensitivity, AUC (area under the ROC curve) [19], in order to measure the effect of using Artificial intelligence in the personalized management of breast cancer was investigated.

Results

As shown in Fig. 1, the database search resulted in the retrieval of 1,033 records until September 2023. After removing duplicate studies and reviewing based on entry indices to the study, ultimately 46 articles that met the entry conditions were selected for review, the specifications of which are mentioned in Table 2. The conducted studies indicate that the data used for modeling through machine learning has had a high diversity. For example, 59% (27 articles) of the reviewed articles used patient medical record data as input, and in four articles (1.847%), biological samples such as genes, molecular samples, and cell classes were reported. In 14 articles (30.4%), genomic data such as gene expression, genetic mutation data, phenotype data, proteomics were used with drug response data as input in artificial intelligence methods. In 12 articles (5.52%), radiomic data (radiography with biological indicators) and in three articles (1.38%), radiogenomic data were used by researchers for the management of neoplasm treatments. However, in 24 articles (52.3%), drug response data was used, indicating the necessity of considering different data dimensions in creating personalized management of breast cancer. The effectiveness of the selected artificial intelligence methods in different studies was examined and is shown in Table 2. The performance of the used methods was evaluated and selected with various indices, including accuracy, precision, sensitivity, feature, AUC. The reported indices showed that the performance of the used methods is at a significant level. Therefore, many of the algorithms used in the studies indicate the ability of artificial intelligence in early detection, predicting response to treatment, patient survival, and screening. Ultimately, the reviews showed that six studies using various artificial intelligence algorithms such as SVM, DNN, ANN, CNN on multi-omics data, one study using ANN, DNN models on omics data, also 10 studies using CNN, DT, XGB, MLP methods on genomics data, 14 studies mostly using SVM, XGB, CNN, RF methods on radiomics, five studies with high frequency using CNN methods on radiogenomics data, 6 studies mostly using RF, CNN algorithms on pharmacogenomics data, two studies using SVM and RF on proteomics data, one study using linear MSKCC model on epigenetic data and one study using GB, XGB, RF on transcriptomic data have achieved acceptable results (indices above 80%).

Table 2 Characteristics of the reviewed articles in the present systematic study
Full size table
Fig. 1
figure 1

PRISMA flow diagram

Full size image

In 11 studies, the Cancer Genome Atlas (TCGA) was used as the data set source. Of these, four studies using CNN achieved high indices in predicting survival and recurrence of breast cancer. This indicates that the designed deep learning networks are superior in terms of comprehensive evaluation over traditional methods. Five studies using machine-learning models such as RF, SVR, and DNN in predicting the response to chemotherapy drugs in these patients reported the desirable performance of these drugs considering the type of tumor and its receptors. These models can be used to predict drug response for some specific drugs and potentially play a complementary role in personalized medicine. Two studies that analyzed and predicted cancer biomarkers on tumor growth in patients using SVM, RF, RE models reported the impact of each with high accuracy. The proposed algorithm improves the cost-effectiveness and accuracy of the screening process compared to current clinical guidelines. In two studies that used machine-learning models such as LASSON, ELASTIC NET, and RR on pharmacogenomics data from the Cancer Cell Line Encyclopedia (CCLE) to predict responsiveness to breast cancer treatment, the area under the ROC curve of the models indicated the desirable performance of the drug on patients. The proposed approach has the potential to enable the design of new hypotheses, improve drug selection, and lead to improvements in patient genomic-based treatments for cancer. Seven studies also analyzed the effect of chemotherapy drugs on drug-sensitive genomic data in cancer (GDSC) using machine learning and deep learning models, each of which reported high indices for their study. In other words, these models provide new methods for predicting anticancer drugs in human tissues and outperform human experts in predictive accuracy. Based on the effectiveness indices, in a large number of selected articles, methods based on SVM and RF, which are linear models, effectively predicted and diagnosed cancer with voluminous genomic data and a high number of feature parameters. Another algorithm used in radiomics articles was the convolutional neural network (CNN), a non-linear deep learning technique that can take an input image and is designed to improve automatic accuracy and provide acceptable efficiency in predicting the impact of pre-surgery chemotherapy (Table 3). In eight studies, the radiomics and multi-omics signature model provided better classification performance using linear and non-linear artificial intelligence methods, with SVM having a higher frequency, which has high accuracy in analyzing complex and voluminous data, compared to radiologists. The striking predictive ability of the radiomics signature is effective for responding to patient treatment.

Table 3 Distribution of applied AI algorithms and their categorizations by frequencies
Full size table

Also, the patterns obtained in radiomics can predict the occurrence of metastasis and response to treatment after neoadjuvant with high indices, the result of which is the selection of appropriate treatment for the patient. Twelve studies that used deep learning techniques on multi-omics, genomics, pharmacogenomics data to predict survival and diagnosis of breast cancer and responsiveness to treatment showed that the proposed policy has this potential with the appropriate selection of drugs, to provide the effectiveness of genomic treatments for breast cancer and has the ability to extract vital data and estimate predictive indices. This model can be used to predict drug response for some specific drugs and potentially play a complementary role in personalized medicine. It can also be a useful tool for determining the translation of gene expression signatures and predicting the status of breast cancer biomarkers on radiogenomics data in clinical decisions for personalized medicine. Most of the studies conducted were for the United States (The results showed that most articles were published in China and the United States and the number of articles published in the field of precision medicine has increased significantly in recent years) (Fig. 2) and the final classification of studies based on the type of activity performed for the personalized management of breast cancer is shown in (Fig. 3). The level of bias in 43 studies included in this review was diagnosed as low risk. Only two citations with medium bias risk [45, 46] and one with high bias risk [55] were evaluated. The questions “Were confounding factors identified?” and “Were there strategies to deal with confounding factors?” were not applicable in our entered studies, as our studies were not experimental.

Fig. 2
figure 2

Frequency of paper in any country

Full size image
Fig. 3
figure 3

The distribution of citation by inputs and type of care

Full size image

Discussion

Hopes for precise pharmacological treatment strategies in breast cancer (BC) and triple-negative breast cancer (TNBC) have been raised by the development of next-generation sequencing technologies, since breast cancer is a heterogeneous disease with various molecular types (e.g., HER2 + and TRPN, or estrogen or progesterone receptor). It is crucial to customize effective treatments for every patient due to the heightened risk of disease recurrence and mortality. Novel and efficacious treatments for metastatic breast cancer have been developed as a result of recent developments in precision medicine. Treatment for each patient is tailored using genomic testing to find genetic mutations that contribute to the growth of breast cancer [66]. Patients with positive BRCA1, 2 gene mutations can avoid metastasis by using targeted therapies that specifically target these genetic mutations. Immunotherapy is another instance of how precision medicine is used to treat metastatic breast cancer. Furthermore, the development of endocrine therapies hormones that promote the growth of breast cancer cells has been aided by precision medicine. A non-invasive procedure called liquid biopsy uses a patient’s blood sample to detect cancer genes or cells. This makes it possible to identify any new mutations that might arise during treatment and to monitor the progression of the disease in a minimally invasive manner. Another area of advancement [67, 68]. Medical decisions are usually associated with various and multiple variables, which make decision-making difficult. For example, oncologists have to combine a large volume of clinical, biological, genome and imaging data to achieve appropriate treatments, while their cognitive capacity can only integrate up to five factors (senses). Therefore, artificial intelligence can facilitate decisions that rely on multiple and diverse variables.

In the present study, 46 articles were selected with the aim of determining the application of artificial intelligence in personalized management of breast cancer. The goal was to select studies that focused on diagnosis, treatment, screening, prognosis, and prediction of disease in breast cancer patients. The aim of 22 studies was to predict the response to treatment and survival of patients. These studies, which had used various types of deep learning techniques, presented high AUC indices, which could indicate that the use of artificial intelligence in predicting the response to treatment and survival of patients has a high ability and this has increased the confidence of researchers. Machine learning techniques such as RF, SVM, XGBoost, which were used to investigate the response to chemotherapy on Pharmacogenomics data of patients, showed that with 100% sensitivity and an average AUC of 0.9, they could predict this process [21]. Therefore, this predictive ability can help doctors and scientists to use effective and alternative drugs for effective treatment of patients. Since predicting the response to neoadjuvant chemotherapy in breast cancer is of high importance and it has been seen that 15% of patients respond negatively to this type of treatment, studies have shown that deep learning techniques such as CNN and VGG16 for predicting the response to neoadjuvant treatment on pathological images and omics data of patients had high index results (SEN = 98%, AUC = 1) [23, 40]. Therefore, with the automation of analysis and reviews, the speed of image analysis increases and the error rate of doctors and specialists decreases. Also, in a study to screen patients, one of the CNN models named U-Net was used to analyze the radiomics data of patients, which had presented 92% and 93% sensitivity and accuracy, respectively. The findings of the measured indices showed that machine learning can also be effective in screening patients. Considering the positive effects of artificial intelligence, one of the challenges of using artificial intelligence in personalized medicine is the lack of available and high-quality data and the lack of participation of the most important variables in modeling, which can lead to the identification of unrelated patterns. On the other hand, ensuring privacy and data security, maintaining ethical considerations are other challenges of using artificial intelligence in analyzing patient data, which artificial intelligence technology in block-chain can increase data management, privacy by facilitating the storage and secure sharing of patient records, medical research data and other sensitive information [69].

To this end, we argue that one of the challenges that medicine faces in personalized management of breast cancer is the problem of drug resistance in patients, which requires looking for alternative treatments, which fortunately artificial intelligence can help doctors in this field [70, 71]. The use of artificial intelligence and analytical techniques can provide new models for predicting the response to disease treatment and be effective in helping doctors choose appropriate personalized treatments by using them in medical decision support systems [72, 73]. Although this research was able to illustrate the artificial intelligence techniques used in breast cancer management, we faced some limitations in conducting this research, one of which was the lack of inclusion of some articles and studies presented at conferences that we did not have access to their full texts. We also only used English articles, so there is a possibility of losing several relevant studies and articles with effective results in non-English languages.

Conclusion

Findings of the present study show that the use of machine learning in the fields of prognosis, diagnosis, prediction, treatment, and screening, which collectively emphasize breast cancer management, have had an effective role, and it can be hoped that the growth of artificial intelligence in the not-too-distant future will provide a very high confidence to healthcare providers to solve patients’ problems. The focus and emphasis on the use of deep learning is not only the recommendation of researchers in the field of breast cancer management with the help of artificial intelligence, but also the present study emphasizes this recommendation. Simultaneously with the integration of patient-specific data and medical knowledge, artificial intelligence systems can provide optimal treatment options and predict treatment outcomes. This capability can help health care providers in making more informed decisions and improving patient care. It can also lead to faster diagnosis, reduced waiting time, faster patient recovery, and ultimately increased efficiency of health care. Following more effective treatment, reduced side effects and improved patient satisfaction, the possibility of discovering new biomarkers and treatment methods are other effects of it. New policies, preventive tactics, diagnosis, and treatment for the appropriate person at the appropriate time will need to be guided by innovative research combined with data science, as well as innovative diagnostic systems for equitable and safe data sharing. One factor to take into account is the accessibility of knowledge in remote areas, particularly the availability of qualified experts when needed. Many examples of enhanced diagnostic capabilities in resource-poor settings, which could result in better patient classification and, ultimately, more individualized treatment planning, have been made possible by artificial intelligence. This feature has the potential to improve patient care by assisting healthcare professionals in making better decisions. Additionally, it may result in quicker patient recovery, a shorter waiting period, quicker diagnoses, and ultimately more efficient health care delivery. There is no doubt that investing in AI now will pay off later on in the form of improved population health and cost savings from precision medicine. In precision public health and medicine, governments are essential because they facilitate the equitable application of knowledge to the development of evidence-based policies, procedures, and environmental modifications. Through error reduction and the potential to significantly reduce the number of missed cancer diagnoses, artificial intelligence offers rich opportunities for designing intelligent systems and medical decision support, thereby creating new services.

Data availability

The datasets used and/or analyses during the current study available from the corresponding author on reasonable request. Declarations Ethics approval and consent to participate Not applicable.

Abbreviations

ER:

Estrogen receptors

DNA:

deoxyribonucleic acid

SPICE:

setting, perspective, intervention, comparison, and evaluation

PICO:

Population, Intervention, Comparison and Outcomes

ACC:

accuracy

SEN:

sensitivity

SPE:

specificity

ROC:

Receiver operating characteristic

AUC:

Area under the ROC curve

MRI:

Magnetic resonance imaging

PET/CT:

positron emission tomography

HER2:

Human epidermal growth factor receptor-2

PR:

progesterone receptor

TCGA-LGG:

The Cancer Genome Atlas Low Grade Glioma

VGG:

Visual Geometry Group

RR:

Ridge regression

LASSO:

least absolute selection and shrinkage operator

DT:

Decision tree

NB:

Naive Bayesian

RF:

Random Forest

LR:

Logistic Regression

DNN:

Deep neural network

UDF:

User defined functions

SVM:

Support Vector Machine

HMF:

hydroxyl methyl furfural

VNN:

Volterra Neural Network

ANN:

Artificial Neural Network

SVR:

Support Vector Regression

TCGA:

the Cancer Genome Atlas

CNN:

Convolutional neural network

NLP:

Natural Language Processing

KNN:

K-nearest neighbor algorithm

CCLE:

Cancer Cell Line Encyclopedia

DeepPT:

Deep Pathology for Treatment

RBM:

Restricted Boltzmann machine

DGUFS:

Unsupervised Feature Selection

GAN:

Generative adversarial network

ROC:

Receiver Operating Characteristic

XGBoost:

extreme Gradient Boosting Tree

GDSC:

Genomics of Drug Sensitivity in Cancer

UFSOL:

Unsupervised Feature Selection with Ordinal Locality

References

  1. Strianese O, Rizzo F, Ciccarelli M, Galasso G, D’Agostino Y, Salvati A, Del Giudice C, Tesorio P, Rusciano MR. Precision and personalized medicine: how genomic approach improves the management of cardiovascular and neurodegenerative disease. Genes. 2020;11(7):747. https://doi.org/10.3390/genes11070747.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Pokorska-Bocci A, Stewart A, Sagoo GS, Hall A, Kroese M, Burton H. Personalized medicine’: what’s in a name? Personalized Med. 2014;11(2):197–210. https://doi.org/10.2217/PME.13.107.

    Article  CAS  Google Scholar 

  3. Olopade OI, Grushko TA, Nanda R, Huo D. Advances in breast cancer: pathways to personalized medicine. Clin Cancer Res. 2008;14(24):7988–99. https://doi.org/10.1158/1078-0432.CCR-08-1211.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Rivenbark AG, O’Connor SM, Coleman WB. Molecular and cellular heterogeneity in breast cancer: challenges for personalized medicine. Am J Pathol. 2013;183(4):1113–24. https://doi.org/10.1016/j.ajpath.2013.08.002.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Malone ER, Oliva M, Sabatini PJ, Stockley TL, Siu LL. Molecular profiling for precision cancer therapies. Genome Med. 2020;12(1):1–9. https://doi.org/10.1186/s13073-019-0703-1.

    Article  Google Scholar 

  6. Gradishar WJ, Moran MS, Abraham J, Aft R, Agnese D, Allison KH, Anderson B, Burstein HJ, Chew H, Dang C, Elias AD. Breast cancer, version 3.2022, NCCN clinical practice guidelines in oncology. J Natl Compr Canc Netw. 2022;20(6):691–722. https://doi.org/10.6004/jnccn.2022.0030.

    Article  PubMed  Google Scholar 

  7. Lewis JE, Kemp ML. Integration of machine learning and genome-scale metabolic modeling identifies multi-omics biomarkers for radiation resistance. Nat Commun. 2021;12(1):2700. https://doi.org/10.1038/s41467-021-22989-1.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Cardoso F, Di Leo A, Lohrisch C, Bernard C, Ferreira F, Piccart MJ. Second and subsequent lines of chemotherapy for metastatic breast cancer: what did we learn in the last two decades? Ann Oncol. 2002;13(2):197–207. https://doi.org/10.1093/annonc/mdf101.

    Article  CAS  PubMed  Google Scholar 

  9. Xu F, Sepúlveda MJ, Jiang Z, Wang H, Li J, Liu Z, Yin Y, Roebuck MC, Shortliffe EH, Yan M, Song Y. Effect of an artificial intelligence clinical decision support system on treatment decisions for complex breast cancer. JCO Clinical Cancer Informatics. 2020;4:824 – 38. https://doi.org/10.1200/CCI.20.00018JCO Clinical.

  10. Xu F, Sepúlveda MJ, Jiang Z, Wang H, Li J, Yin Y, Liu Z, Roebuck MC, Shortliffe EH, Yan M, Song Y. Artificial intelligence treatment decision support for complex breast cancer among oncologists with varying expertise. JCO Clinical Cancer Informatics. 2019;3:1–5. https://doi.org/10.1200/CCI.18.00159JCO Clinical.

  11. Chan HP, Samala RK, Hadjiiski LM. CAD and AI for breast cancer—recent development and challenges. Br J Radiol. 2019;93(1108):20190580. https://doi.org/10.1259/bjr.20190580.

    Article  PubMed  PubMed Central  Google Scholar 

  12. Nagahashi M, Shimada Y, Ichikawa H, Kameyama H, Takabe K, Okuda S, Wakai T. Next generation sequencing-based gene panel tests for the management of solid tumors. Cancer Sci. 2019;110(1):6–15. https://doi.org/10.1111/cas.13837.

    Article  CAS  PubMed  Google Scholar 

  13. Nagarajan N, Yapp EK, Le NQ, Kamaraj B, Al-Subaie AM, Yeh HY. Application of computational biology and artificial intelligence technologies in cancer precision drug discovery. Biomed Res Int. 2019;2019. https://doi.org/10.1155/2019/8427042.

  14. Barros V, Tlusty T, Barkan E, Hexter E, Gruen D, Guindy M, Rosen-Zvi M. Virtual biopsy by using artificial intelligence–based multimodal modeling of binational mammography data. Radiology. 2022;306(3):e220027. https://doi.org/10.1148/radiol.220027.

    Article  PubMed  Google Scholar 

  15. Wada N, Nakashima M, Uchiyama Y. Analysis of the relationship between image and blood examinations in an artificial intelligence system for the molecular diagnosis of breast cancer. Open J Appl Sci. 2021;11(9):1016–27. https://doi.org/10.4236/ojapps.2021.119074.

    Article  CAS  Google Scholar 

  16. Sarkis-Onofre R, Catalá-López F, Aromataris E, Lockwood C. How to properly use the PRISMA Statement. Syst Reviews. 2021;10(1):1–3. https://doi.org/10.1186/s13643-021-01671-z.

    Article  Google Scholar 

  17. Davies KS. Formulating the evidence based practice question: a review of the frameworks. Evid Based Libr Inform Pract. 2011;6(2):75–80. https://doi.org/10.18438/B8WS5N.

    Article  Google Scholar 

  18. Jun H, Yoon SH, Roh M, Kim SH, Lee J, Lee J, Kwon M, Leem J. Quality assessment and implications for further study of acupotomy: case reports using the case report guidelines and the Joanna Briggs Institute critical appraisal checklist. J Acupunct Res. 2021;38(2):122–33. https://doi.org/10.13045/jar.2021.00024.

    Article  Google Scholar 

  19. Midgley AR Jr, Niswender GD, Rebar RW. Principles for the assessment of the reliability of radioimmunoassay methods (precision, accuracy, sensitivity, specificity). Eur J Endocrinol. 1969;62(1Supplement):S163–84. https://doi.org/10.1530/acta.0.062S163.

    Article  Google Scholar 

  20. Tong L, Mitchel J, Chatlin K, Wang MD. Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis. BMC Med Inf Decis Mak. 2020;20:1–2. https://doi.org/10.1186/s12911-020-01225-8.

    Article  Google Scholar 

  21. Lee KM, Lee H, Han D, Moon WK, Kim K, Oh HJ, Choi J, Hwang EH, Kang SE, Im SA, Lee KH. Combined the SMAC mimetic and BCL2 inhibitor sensitizes neoadjuvant chemotherapy by targeting necrosome complexes in tyrosine aminoacyl-tRNA synthase-positive breast cancer. Breast Cancer Res. 2020;22:1–13. https://doi.org/10.1186/s13058-020-01367-7.

    Article  CAS  Google Scholar 

  22. Amiri Souri E, Chenoweth A, Cheung A, Karagiannis SN, Tsoka S. Cancer Grade Model: a multi-gene machine learning-based risk classification for improving prognosis in breast cancer. Br J Cancer. 2021;125(5):748–58. https://doi.org/10.1038/s41416-021-01455-1.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Sharma S, Mehra R. Conventional machine learning and deep learning approach for multi-classification of breast cancer histopathology images—a comparative insight. J Digit Imaging. 2020;33(3):632–54. https://doi.org/10.1007/s10278-019-00307-y.

    Article  PubMed  PubMed Central  Google Scholar 

  24. Sammut SJ, Crispin-Ortuzar M, Chin SF, Provenzano E, Bardwell HA, Ma W, Cope W, Dariush A, Dawson SJ, Abraham JE, Dunn J, Hiller L, Thomas J, Cameron DA, Bartlett JMS, Hayward L, Pharoah PD, Markowetz F, Rueda OM, Earl HM, Caldas C. Multi-omic machine learning predictor of breast cancer therapy response. Nature. 2022;601(7894):623–9. https://doi.org/10.1038/s41586-021-04278-5.

    Article  CAS  PubMed  Google Scholar 

  25. Meti N, Saednia K, Lagree A, Tabbarah S, Mohebpour M, Kiss A, Lu FI, Slodkowska E, Gandhi S, Jerzak KJ, Fleshner L, Law E, Sadeghi-Naini A, Tran WT. Machine learning frameworks to Predict Neoadjuvant Chemotherapy response in breast Cancer using clinical and pathological features. JCO Clin Cancer Inf. 2021;5:66–80. https://doi.org/10.1200/CCI.20.00078.

    Article  Google Scholar 

  26. Nguyen LC, Naulaerts S, Bruna A, Ghislat G, Ballester PJ. Predicting Cancer Drug response in vivo by learning an optimal feature selection of Tumour Molecular profiles. Biomedicines. 2021;9(10):1319. https://doi.org/10.3390/biomedicines9101319.

    Article  PubMed  PubMed Central  Google Scholar 

  27. Ramkumar C, Buturovic L, Malpani S, Kumar Attuluri A, Basavaraj C, Prakash C, Madhav L, Doval DC, Mehta A, Bakre MM. Development of a novel proteomic risk-classifier for prognostication of patients with early-stage hormone receptor–positive breast Cancer. Biomark Insights. 2018;13:1177271918789100. https://doi.org/10.1177/1177271918789100.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Brocato TA, Brown-Glaberman U, Wang Z, Selwyn RG, Wilson CM, Wyckoff EF, Lomo LC, Saline JL, Hooda-Nehra A, Pasqualini R, Arap W, Brinker CJ, Cristini V. Predicting breast cancer response to neoadjuvant chemotherapy based on tumor vascular features in needle biopsies. JCI Insight. 2019;5(8):e126518. https://doi.org/10.1172/jci.insight.126518.

    Article  PubMed  Google Scholar 

  29. Roy S, Whitehead TD, Li S, Ademuyiwa FO, Wahl RL, Dehdashti F, Shoghi KI. Co-clinical FDG-PET radiomic signature in predicting response to neoadjuvant chemotherapy in triple-negative breast cancer. Eur J Nucl Med Mol Imaging. 2022;49(2):550–62. https://doi.org/10.1007/s00259-021-05489-8.

    Article  CAS  PubMed  Google Scholar 

  30. Mehmood A, Nawab S, Jin Y, Hassan H, Kaushik AC, Wei DQ. Ranking breast Cancer drugs and biomarkers Identification using machine learning and Pharmacogenomics. ACS Pharmacol Translational Sci. 2023 Feb;24. https://doi.org/10.1021/acsptsci.2c00212.

  31. Farahmand S, Fernandez AI, Ahmed FS, Rimm DL, Chuang JH, Reisenbichler E, Zarringhalam K. Deep learning trained on hematoxylin and eosin tumor region of interest predicts HER2 status and trastuzumab treatment response in HER2 + breast cancer. Mod Pathol. 2022;35(1):44–51. https://doi.org/10.1038/s41379-021-00911-w.

    Article  CAS  PubMed  Google Scholar 

  32. Webber JT, Kaushik S, Bandyopadhyay S. Integration of tumor genomic data with cell lines using multi-dimensional network modules improves cancer pharmacogenomics. Cell Syst. 2018;7(5):526–36. https://doi.org/10.1016/j.cels.2018.10.001.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. Li F, Yang Y, Wei Y, He P, Chen J, Zheng Z, Bu H. Deep learning-based predictive biomarker of pathological complete response to neoadjuvant chemotherapy from histological images in breast cancer. J Translational Med. 2021;19(1):1–3.

    Article  Google Scholar 

  34. Bitencourt AG, Gibbs P, Saccarelli CR, Daimiel I, Gullo RL, Fox MJ, Thakur S, Pinker K, Morris EA, Morrow M, Jochelson MS. MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer. EBioMedicine. 2020;61:103042. https://doi.org/10.2139/ssrn.3582723.

    Article  PubMed  PubMed Central  Google Scholar 

  35. Orozco JI, Le J, Ensenyat-Mendez M, Baker JL, Weidhaas J, Klomhaus A, Marzese DM, DiNome ML. Machine learning-based epigenetic classifiers for axillary staging of patients with ER-positive early-stage breast cancer. Ann Surg Oncol. 2022;29(10):6407–14. https://doi.org/10.1245/s10434-022-12143-6.

    Article  PubMed  PubMed Central  Google Scholar 

  36. Gupta S, Gupta MK. A comparative analysis of deep learning approaches for predicting breast cancer survivability. Arch Comput Methods Eng. 2022;29(5):2959–75. https://doi.org/10.1007/s11831-021-09679-3.

    Article  Google Scholar 

  37. Malik V, Kalakoti Y, Sundar D. Deep learning assisted multi-omics integration for survival and drug-response prediction in breast cancer. BMC Genomics. 2021;22:1–1. https://doi.org/10.1186/s12864-021-07524-2.

    Article  CAS  Google Scholar 

  38. Hoang DT, Dinstag G, Hermida LC, Ben-Zvi DS, Elis E, Caley K, Sinha S, Sinha N, Dampier CH, Beker T, Aldape K. Synthetic lethality-based prediction of cancer treatment response from histopathology images. bioRxiv. 2022 Jan 1. https://doi.org/10.1101/2022.06.07.495219.

  39. Mourragui SM, Loog M, Vis DJ, Moore K, Manjon AG, van de Wiel MA, Reinders MJ, Wessels LF. Predicting patient response with models trained on cell lines and patient-derived xenografts by nonlinear transfer learning. Proc Natl Acad Sci. 2021;118(49):e2106682118. https://doi.org/10.1073/pnas.2106682118.

  40. Kuenzi BM, Park J, Fong SH, Sanchez KS, Lee J, Kreisberg JF, Ma J, Ideker T. Predicting drug response and synergy using a deep learning model of human cancer cells. Cancer Cell. 2020;38(5):672–84. https://doi.org/10.1016/j.ccell.2020.09.014.

  41. Sharifi Noghabi H. Deep transfer learning for drug response prediction (Doctoral dissertation, Applied Sciences: School of Computing Science).

  42. Sharifi-Noghabi H, Zolotareva O, Collins CC, Ester M. MOLI: multi-omics late integration with deep neural networks for drug response prediction. Bioinformatics. 2019;35(14):i501–9. https://doi.org/10.1093/bioinformatics/btz318.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Liu Q, Muglia LJ, Huang LF. Network as a biomarker: a novel network-based sparse bayesian machine for pathway-driven drug response prediction. Genes. 2019;10(8):602. https://doi.org/10.3390/genes10080602.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Sammut SJ, Crispin-Ortuzar M, Chin SF, Provenzano E, Bardwell HA, Ma W, Cope W, Dariush A, Dawson SJ, Abraham JE, Dunn J. Multi-omic machine learning predictor of breast cancer therapy response. Nature. 2022;601(7894):623–9. https://doi.org/10.1038/s41586-021-04278-5.

    Article  CAS  PubMed  Google Scholar 

  45. Saha A, Harowicz MR, Grimm LJ, Kim CE, Ghate SV, Walsh R, Mazurowski MA. A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features. Br J Cancer. 2018;119(4):508–16. https://doi.org/10.1038/s41416-018-0185-8.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. McAnena P, Moloney BM, Browne R, O’Halloran N, Walsh L, Walsh S, Sheppard D, Sweeney KJ, Kerin MJ, Lowery AJ. A radiomic model to classify response to neoadjuvant chemotherapy in breast cancer. BMC Med Imaging. 2022;22(1):1–9.

    Article  Google Scholar 

  47. Li Q, Xiao Q, Li J, Wang Z, Wang H, Gu Y. Value of machine learning with multiphases Ce-Mri radiomics for early prediction of pathological complete response to neoadjuvant therapy in her2-positive invasive breast cancer. Cancer Manage Res. 2021;5053–62. https://doi.org/10.2147/CMAR.S304547.

  48. Bitencourt AG, Gibbs P, Saccarelli CR, Daimiel I, Gullo RL, Fox MJ, Thakur S, Pinker K, Morris EA, Morrow M, Jochelson MS. MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer. EBioMedicine. 2020;61:103042. https://doi.org/10.1016/j.ebiom.2020.103042.

    Article  PubMed  PubMed Central  Google Scholar 

  49. Yu Y, He Z, Ouyang J, Tan Y, Chen Y, Gu Y, Mao L, Ren W, Wang J, Lin L, Wu Z. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study. Volume 69. EBioMedicine; 2021. p. 103460. https://doi.org/10.1016/j.ebiom.2021.103460.

  50. Vigil N, Barry M, Amini A, Akhloufi M, Maldague XP, Ma L, Ren L, Yousefi B. Dual-intended deep learning model for breast Cancer diagnosis in Ultrasound Imaging. Cancers. 2022;14(11):2663.

    Article  PubMed  PubMed Central  Google Scholar 

  51. Militello C, Rundo L, Dimarco M, Orlando A, Woitek R, D’Angelo I, Russo G, Bartolotta TV. 3D DCE-MRI radiomic analysis for malignant lesion prediction in breast cancer patients. Acad Radiol. 2022;29(6):830–40. https://doi.org/10.1016/j.acra.2021.08.024.

    Article  PubMed  Google Scholar 

  52. Park EK, Lee KS, Seo BK, Cho KR, Woo OH, Son GS, Lee HY, Chang YW. Machine learning approaches to radiogenomics of breast cancer using low-dose perfusion computed tomography: predicting prognostic biomarkers and molecular subtypes. Sci Rep. 2019;9(1):1–1. https://doi.org/10.1038/s41598-019-54371-z.

    Article  CAS  Google Scholar 

  53. Nguyen L, Naulaerts S, Bomane A, Bruna A, Ghislat G, Ballester PJ. Machine learning models to predict in vivo drug response via optimal dimensionality reduction of tumour molecular profiles. bioRxiv 2018 Jan 1:277772. https://doi.org/10.1101/277772.

  54. Dutta K, Roy S, Whitehead TD, Luo J, Jha AK, Li S, Quirk JD, Shoghi KI. Deep learning segmentation of triple-negative breast cancer (TNBC) patient derived tumor xenograft (PDX) and sensitivity of radiomic pipeline to tumor probability boundary. Cancers. 2021;13(15):3795. https://doi.org/10.3390/cancers13153795.

    Article  PubMed  PubMed Central  Google Scholar 

  55. Zhang Y, You C, Pei Y, Yang F, Li D, Jiang YZ, Shao Z. Integration of radiogenomic features for early prediction of pathological complete response in patients with triple-negative breast cancer and identification of potential therapeutic targets. J Translational Med. 2022;20(1):256. https://doi.org/10.1186/s12967-022-03452-1.

    Article  CAS  Google Scholar 

  56. Chen J, Hao L, Qian X, Lin L, Pan Y, Han X. Machine learning models based on immunological genes to predict the response to neoadjuvant therapy in breast cancer patients. Front Immunol. 2022;13. https://doi.org/10.3389/fimmu.2022.948601.

  57. Caballo M, Pangallo DR, Mann RM, Sechopoulos I. Deep learning-based segmentation of breast masses in dedicated breast CT imaging: radiomic feature stability between radiologists and artificial intelligence. Comput Biol Med. 2020;118:103629. https://doi.org/10.1016/j.compbiomed.2020.103629.

    Article  PubMed  PubMed Central  Google Scholar 

  58. Pang T, Wong JH, Ng WL, Chan CS. Semi-supervised GAN-based radiomics model for data augmentation in breast ultrasound mass classification. Comput Methods Programs Biomed. 2021;203:106018. https://doi.org/10.1016/j.cmpb.2021.106018.

    Article  PubMed  Google Scholar 

  59. Ma S, Ren J, Fenyö D. Breast cancer prognostics using multi-omics data. AMIA summits on translational science proceedings. 2016;2016:52. PMCID: PMC5001766.

  60. Braman NM, Etesami M, Prasanna P, Dubchuk C, Gilmore H, Tiwari P, Plecha D, Madabhushi A. Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res. 2017;19(1):1–4. https://doi.org/10.1186/s13058-017-0846-1.

    Article  CAS  Google Scholar 

  61. Cui H, Sun Y, Zhao D, Zhang X, Kong H, Hu N, Wang P, Zuo X, Fan W, Yao Y, Fu B. Radiogenomic analysis of prediction HER2 status in breast cancer by linking ultrasound radiomic feature module with biological functions. J Translational Med. 2023;21(1):1–5. https://doi.org/10.21203/rs.3.rs-1695912/v1.

    Article  Google Scholar 

  62. Tyanova S, Albrechtsen R, Kronqvist P, Cox J, Mann M, Geiger T. Proteomic maps of breast cancer subtypes. Nature communications. 2016;7(1):10259. | https://doi.org/10.1038/ncomms10259.

  63. Yanovich G, Agmon H, Harel M, Sonnenblick A, Peretz T, Geiger T. Clinical proteomics of breast cancer reveals a novel layer of breast cancer classification. Cancer Res. 2018;78(20):6001–10. https://doi.org/10.1158/0008-5472.CAN-18-1079.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  64. Wang Z, Li R, Wang M, Li A. GPDBN: deep bilinear network integrating both genomic data and pathological images for breast cancer prognosis prediction. Bioinformatics. 2021;37(18):2963–70. https://doi.org/10.1093/bioinformatics/btab185.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  65. Azzouz FB, Michel B, Lasla H, Gouraud W, François AF, Girka F, Lecointre T, Guérin-Charbonnel C, Juin PP, Campone M, Jézéquel P. Development of an absolute assignment predictor for triple-negative breast cancer subtyping using machine learning approaches. Comput Biol Med. 2021;129:104171. https://doi.org/10.1101/2020.06.02.129544.

    Article  PubMed  Google Scholar 

  66. Subhan MA, Parveen F, Shah H, Yalamarty SS, Ataide JA, Torchilin VP. Recent advances with precision medicine treatment for breast cancer including triple-negative sub-type. Cancers. 2023;15(8):2204.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  67. Zhang X, Yang H, Zhang R. Challenges and future of precision medicine strategies for breast cancer based on a database on drug reactions. Biosci Rep. 2019;39(9):BSR20190230.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  68. Rodrigues-Ferreira S, Nahmias C. Predictive biomarkers for personalized medicine in breast cancer. Cancer Lett. 2022;545:215828.

    Article  CAS  PubMed  Google Scholar 

  69. Pesapane F, Volonté C, Codari M, Sardanelli F. Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United States. Insights into Imaging. 2018;9:745–53. https://doi.org/10.1007/s13244-018-0645-y.

    Article  PubMed  PubMed Central  Google Scholar 

  70. Chan CW, Law BM, So WK, Chow KM, Waye MM. Novel strategies on personalized medicine for breast cancer treatment: an update. Int J Mol Sci. 2017;18(11):2423.

    Article  PubMed  PubMed Central  Google Scholar 

  71. Tran WT, Jerzak K, Lu FI, Klein J, Tabbarah S, Lagree A, Wu T, Rosado-Mendez I, Law E, Saednia K, Sadeghi-Naini A. Personalized breast cancer treatments using artificial intelligence in radiomics and pathomics. J Med Imaging Radiation Sci. 2019;50(4):S32–41.

    Article  Google Scholar 

  72. Rodrigues-Ferreira S, Nahmias C. Predictive biomarkers for personalized medicine in breast cancer. Cancer Lett 2022 Jul 16:215828.

  73. Nagarajan N, Yapp EK, Le NQ, Kamaraj B, Al-Subaie AM, Yeh HY. Application of computational biology and artificial intelligence technologies in cancer precision drug discovery. BioMed research international. 2019;2019.

Download references

Acknowledgements

Not applicable.

Funding

We don’t have an any funding.

Author information

Authors and Affiliations

  1. Department of Health Information Technology and Management, Medical Informatics, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran

    Solmaz Sohrabei & Hamid Moghaddasi

  2. Department of Health Information Technology and Management, Health Information Management, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran

    Azamossadat Hosseini

  3. Department of English Language, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran

    Seyed Jafar Ehsanzadeh

Authors
  1. Solmaz Sohrabei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hamid Moghaddasi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Azamossadat Hosseini
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Seyed Jafar Ehsanzadeh
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

H.M. and S.S. designed the study and wrote the main manuscript text. All authors reviewed the manuscript.

Corresponding authors

Correspondence to Hamid Moghaddasi or Azamossadat Hosseini.

Ethics declarations

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sohrabei, S., Moghaddasi, H., Hosseini, A. et al. Investigating the effects of artificial intelligence on the personalization of breast cancer management: a systematic study. BMC Cancer 24, 852 (2024). https://doi.org/10.1186/s12885-024-12575-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1186/s12885-024-12575-1

Keywords

BMC Cancer

ISSN: 1471-2407

Contact us